9 1 231

Async0x42

async0x42

async0x42

AI & ML interests

None yet

Recent Activity

liked a model 6 days ago

huihui-ai/QwQ-32B-abliterated

liked a model 6 days ago

TheDrummer/Cydonia-24B-v2.1-GGUF

liked a model 6 days ago

TheDrummer/Cydonia-24B-v2.1

View all activity

Organizations

None yet

async0x42's activity

liked 3 models 6 days ago

liked a model 7 days ago

calcuis/wan-gguf

Text-to-Video • Updated about 3 hours ago • 62.9k • 43

New activity in bartowski/Qwen_QwQ-32B-GGUF 8 days ago

Bartowski! 0.0!!!! You are on double-secret probation for this jinja error!

#4 opened 8 days ago by

rkh661

liked 2 models 8 days ago

spow12/ChatWaifu_12B_v2.0

Text Generation • Updated Oct 14, 2024 • 60 • 20

Qwen/QwQ-32B

Text Generation • Updated 2 days ago • 256k • • 2.09k

updated a model 12 days ago

async0x42/Wayfarer-Large-70B-Llama-3.3-exl2_4.0bpw

Text Generation • Updated 12 days ago • 18

published a model 12 days ago

async0x42/Wayfarer-Large-70B-Llama-3.3-exl2_4.0bpw

Text Generation • Updated 12 days ago • 18

updated a model 12 days ago

async0x42/Wayfarer-Large-70B-Llama-3.3-exl2_3.5bpw

Text Generation • Updated 12 days ago • 11 • 1

published a model 12 days ago

async0x42/Wayfarer-Large-70B-Llama-3.3-exl2_3.5bpw

Text Generation • Updated 12 days ago • 11 • 1

updated a model 12 days ago

async0x42/CardProjector-24B-v1-exl2_4.65bpw

Updated 12 days ago • 8

published a model 12 days ago

async0x42/CardProjector-24B-v1-exl2_4.65bpw

Updated 12 days ago • 8

reacted to jasoncorkill's post with ❤️ 13 days ago

Post

3823

Has OpenGVLab Lumina Outperformed OpenAI’s Model?

We’ve just released the results from a large-scale human evaluation (400k annotations) of OpenGVLab’s newest text-to-image model, Lumina. Surprisingly, Lumina outperforms OpenAI’s DALL-E 3 in terms of alignment, although it ranks #6 in our overall human preference benchmark.

To support further development in text-to-image models, we’re making our entire human-annotated dataset publicly available. If you’re working on model improvements and need high-quality data, feel free to explore.

We welcome your feedback and look forward to any insights you might share!

Rapidata/OpenGVLab_Lumina_t2i_human_preference